Downloads · 30 days
5
7% of all-time downloads
llama-3.1-8b-instruct-rmu-gambling
shirasko/llama-3.1-8b-instruct-rmu-gambling
llama-3.1-8b-instruct-rmu-gambling is a text generation model from shirasko. Use it when you need the model to write or continue text. It is set up for transformers.
All-time downloads
74
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Aug 1, 2026
- Updated
- Aug 10, 2026
- SHA
- aa2fb1c1
Try a prompt
Base models
Model card
From the Hugging Face model README
Unlearned Checkpoint
| Field | Value |
|---|---|
| Unlearning method | RMU |
| Base model | meta-llama/Llama-3.1-8B-Instruct |
| Target concept | Gambling |
| Checkpoint type | Full Model Weights |
| Rank / seed | 200 / 42 |
| Train eval protocol | mc |
Unlearning Configuration
Selected hyperparameters (from unlearned_checkpoints.json):
| Parameter | Value |
|---|---|
alpha | 50 |
delta_embed | 0 |
k_features_embed | 0 |
layer_id | 7 |
layer_ids | 5,6,7 |
lr | 0.0003 |
n_tokens_edited | 0 |
param_ids | 6 |
setting_name | S1_lid7_L567 |
steering | 30 |
Primary Unlearning Metrics (held-out test, MC protocol)
Headline scores used for checkpoint selection:
| Metric | Train (after unlearning) | Test (after unlearning) |
|---|---|---|
| Efficacy | 1 | 1 |
| Specificity | 0.946 | 0.909 |
| Harmonic mean | 0.972 | 0.952 |
| Relearning QA (MC) | — | 0.78 |
Full Evaluation (baseline → unlearned)
From evaluation/score_comparison.csv:
| Metric | Baseline (train) | After unlearn (train) | Baseline (test) | After unlearn (test) |
|---|---|---|---|---|
| QA accuracy | 0.84 | 0.02 | 0.92 | 0.02 |
| QA fraction | 1 | 0 | 1 | 0 |
| SimDom accuracy | 0.98 | 0.94 | 1 | 0.92 |
| SimDom fraction | 1 | 0.945 | 1 | 0.893 |
| MMLU accuracy | 0.62 | 0.6 | 0.65 | 0.62 |
| MMLU fraction | 1 | 0.946 | 1 | 0.925 |
Files in This Repository
| File | Description |
|---|---|
unlearned_checkpoints.json | Checkpoint metadata & hyperparameters |
evaluation/evaluation_summary.json | Full evaluation payload (train/test/relearning) |
evaluation/score_comparison.csv | Baseline vs. unlearned comparison table |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Languages
- en
- Created
- Aug 1, 2026
- Updated
- Aug 10, 2026